Hi All, I have a question about the output from the bumphunter package. Can I take all the regions in $tab as significant bumps or is there any other cut-off that I need to apply? Thanking you in advance, Khadeeja [[alternative HTML version deleted]]

You need to do permutation testing, by setting B=some number. Kasper On Mon, Feb 18, 2013 at 9:48 AM, khadeeja ismail <hajjja at="" yahoo.com=""> wrote: > Hi All, > I have a question about the output from the bumphunter package. Can I take all the regions in $tab as significant bumps or is there any other cut-off that I need to apply? > Thanking you in advance, > Khadeeja > [[alternative HTML version deleted]] > > _______________________________________________ > Bioconductor mailing list > Bioconductor at r-project.org > https://stat.ethz.ch/mailman/listinfo/bioconductor > Search the archives: http://news.gmane.org/gmane.science.biology.informatics.conductor

This is the difference between the devel (manual) version and the stable version you seem to have installed. If you want to use this, you should really switch to devel because we have changed it for the better. Kasper On Thu, Feb 21, 2013 at 9:40 AM, khadeeja ismail <hajjja at="" yahoo.com=""> wrote: > Hi Kasper, > > This is probably a very silly question. > > The example given in the bumphunter manual shows the following headers in > the results: >> tab$table > ... p.value fwer p.valueArea fwerArea > > > > But headers are different in the tab$table I get. > ... rate, perRunRate, areaRate, areaPerRunRate, . > > The Rate and areaRate colums have values greater than 1, so are the other > two columns (perRunRate, areaPerRunRate ) p.value and FWER for each region? > > I cannot find any details in the manual or user guide about these. Would be > great if you could kindly explain what they are > > > Best regards, > Khadeeja > > > > > > ________________________________ > From: Kasper Daniel Hansen <kasperdanielhansen at="" gmail.com=""> > To: khadeeja ismail <hajjja at="" yahoo.com=""> > Cc: bioconductor bioconductor <bioconductor at="" r-project.org=""> > Sent: Tuesday, February 19, 2013 6:54 PM > > Subject: Re: [BioC] Bumphunter output > > Ok, then your output should include some measure of significance, > which has changed a bit recently. You need to select regions that > have a low FWER, or however you want to do. But it is important to > understand that the output is merely candidate regions and (if you do > permutation testing) each region should have some associated measure > of significance. > > Kasper > > On Mon, Feb 18, 2013 at 10:12 AM, khadeeja ismail <hajjja at="" yahoo.com=""> wrote: >> But the bumphunter function does that, right? I set B to 1000. >> Khadeeja >> >> >> ________________________________ >> From: Kasper Daniel Hansen <kasperdanielhansen at="" gmail.com=""> >> To: khadeeja ismail <hajjja at="" yahoo.com=""> >> Cc: "bioconductor at r-project.org" <bioconductor at="" r-project.org=""> >> Sent: Monday, February 18, 2013 5:09 PM >> Subject: Re: [BioC] Bumphunter output >> >> You need to do permutation testing, by setting B=some number. >> >> Kasper >> >> On Mon, Feb 18, 2013 at 9:48 AM, khadeeja ismail <hajjja at="" yahoo.com=""> wrote: >>> Hi All, >>> I have a question about the output from the bumphunter package. Can I >>> take >>> all the regions in $tab as significant bumps or is there any other >>> cut-off >>> that I need to apply? >>> Thanking you in advance, >>> Khadeeja >>> [[alternative HTML version deleted]] >>> >>> _______________________________________________ >>> Bioconductor mailing list >>> Bioconductor at r-project.org >>> https://stat.ethz.ch/mailman/listinfo/bioconductor >>> Search the archives: >>> http://news.gmane.org/gmane.science.biology.informatics.conductor >> >> > >